INDEX

Explanations

id

np_max-act · gemini-2.0-flash

The neuron fires on tokens that appear inside method‐ or function‐signature parameter lists (e.g. parameter names and types such as “id,” numeric tokens, and punctuation within parentheses).

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

successfully

-0.07

 stance

-0.07

BASH

-0.06

mik

-0.06

 revoked

-0.06

this

-0.06

ZW

-0.06

 Ли

-0.06

 passage

-0.06

CreatedAt

-0.06

POSITIVE LOGITS

 Yugoslavia

0.07

-inflammatory

0.07

очек

0.06

勢

0.06

ifique

0.06

igmat

0.06

 denying

0.06

)++;↵

0.06

χία

0.06

 декабря

0.06

Activations Density 0.020%

id

The neuron fires on tokens that appear inside method‐ or function‐signature parameter lists (e.g. parameter names and types such as “id,” numeric tokens, and punctuation within parentheses).

No Comments

No Known Activations

id

The neuron fires on tokens that appear inside method‐ or function‐signature parameter lists (e.g. parameter names and types such as “id,” numeric tokens, and punctuation within parentheses).

No Comments

No Known Activations