INDEX

Explanations

Technical/formal writing

np_max-act · gemini-2.0-flash

statements involving accusations or legal actions.

oai_token-act-pair · gpt-4o-mini Triggered by @xinyanhu8

The neuron activates on the word “entailed,” i.e. it detects occurrences of that specific term.

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

-0.08

Es

-0.07

 bilgileri

-0.07

()</

-0.07

スト

-0.07

↵    
↵

-0.06

 embryos

-0.06

 fileInfo

-0.06

Prot

-0.06

emploi

-0.06

POSITIVE LOGITS

_pose

0.06

 gotta

0.06

_sk

0.06

:start

0.06

 περ

0.06

(sort

0.06

(group

0.06

 контра

0.06

Activations Density 0.000%

Technical/formal writing

statements involving accusations or legal actions.

The neuron activates on the word “entailed,” i.e. it detects occurrences of that specific term.

No Comments

No Known Activations