INDEX

Explanations

Searching

np_max-act · gemini-2.0-flash

The neuron selectively lights up on words and phrases signaling a search or inquiry—terms like “hope,” “finding,” “who could explain,” and “what”—i.e. language around looking for information or answers.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 отд

-0.07

mach

-0.06

Seattle

-0.06

Ply

-0.06

-city

-0.06

.fixed

-0.06

 reprodu

-0.06

 Basil

-0.06

_ref

-0.06

 Prel

-0.06

POSITIVE LOGITS

?↵↵

0.07

 "'",

0.06

ाइल

0.06

.).↵↵

0.06

웨어

0.06

 خلال

0.06

restore

0.06

quire

0.06

arshal

0.06

gone

0.06

Activations Density 0.039%

Searching

The neuron selectively lights up on words and phrases signaling a search or inquiry—terms like “hope,” “finding,” “who could explain,” and “what”—i.e. language around looking for information or answers.

No Comments

No Known Activations

Searching

The neuron selectively lights up on words and phrases signaling a search or inquiry—terms like “hope,” “finding,” “who could explain,” and “what”—i.e. language around looking for information or answers.

No Comments

No Known Activations