INDEX

Explanations

code and math

np_max-act · gemini-2.0-flash

This neuron is effectively “dead” and does not detect any features.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

比較

-0.06

 tả

-0.06

 Latter

-0.06

BOX

-0.06

วล

-0.06

 prompting

-0.06

 zajist

-0.06

 Мы

-0.06

 degli

-0.05

 Rudy

-0.05

POSITIVE LOGITS

Show

0.07

 Ди

0.07

 seviy

0.07

 Ancient

0.07

Insn

0.06

_APPRO

0.06

 jednou

0.06

-aware

0.06

UIApplication

0.06

Activations Density 0.029%

code and math

This neuron is effectively “dead” and does not detect any features.

No Comments

No Known Activations