INDEX

Explanations

references to social roles and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĺ¯ä¸Ģä¸ª

-0.16

orta

-0.15

ptron

-0.15

æĺ¯ä¸ª

-0.15

ivol

-0.15

 kendisi

-0.15

 itself

-0.14

Traits

-0.14

-rays

-0.14

etri

-0.14

POSITIVE LOGITS

 respective

0.45

 their

0.42

 respectively

0.39

Their

0.36

 themselves

0.35

their

0.35

 Their

0.35

 leurs

0.34

 ihre

0.30

 histories

0.29

Activations Density 0.973%

references to social roles and responsibilities

No Comments

No Known Activations

references to social roles and responsibilities

No Comments

No Known Activations