INDEX

Explanations

phone calls

np_max-act · gemini-2.0-flash

The neuron activates on mentions of phones and making phone calls.

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

 antis

-0.07

モン

-0.07

 Clarence

-0.07

씨

-0.07

.";↵↵

-0.07

 Anti

-0.06

 вимог

-0.06

 الحل

-0.06

")->

-0.06

 Maur

-0.06

POSITIVE LOGITS

raft

0.07

OPSIS

0.06

są

0.06

'nda

0.06

_shapes

0.06

ły

0.06

>About

0.06

 happen

0.06

 Swarm

0.06

 prepare

0.06

Activations Density 0.043%

phone calls

The neuron activates on mentions of phones and making phone calls.

No Comments

No Known Activations

phone calls

The neuron activates on mentions of phones and making phone calls.

No Comments

No Known Activations