INDEX

Explanations

mentions of job-related terms or the creation of jobs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

pag

-0.16

vil

-0.16

ahoma

-0.15

gypt

-0.15

amat

-0.15

Ħìŀ¬

-0.15

omal

-0.14

af

-0.14

POSITIVE LOGITS

sworth

0.17

 Lawson

0.15

 Laden

0.15

ouser

0.15

/mol

0.15

eur

0.15

krit

0.14

agne

0.14

LANG

0.14

eca

0.14

Activations Density 0.010%

mentions of job-related terms or the creation of jobs

No Comments

No Known Activations