INDEX

Explanations

references to law enforcement and government officials

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

FRING

-0.16

kus

-0.15

Stamped

-0.15

Ð·Ð²

-0.15

 rÃ¡m

-0.15

DownList

-0.14

gnore

-0.14

CED

-0.14

TEL

-0.14

$MESS

-0.14

POSITIVE LOGITS

ipo

0.15

ãĥ¼

0.15

 loft

0.15

uter

0.15

sun

0.15

Wig

0.15

tad

0.15

azzi

0.14

iju

0.14

Activations Density 0.074%

references to law enforcement and government officials

No Comments

No Known Activations