INDEX

Explanations

phrases that indicate personal inquiry or actions related to self

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ansa

-0.15

arts

-0.15

umi

-0.15

ksam

-0.15

endent

-0.14

ernes

-0.14

Ã¼mÃ¼ÅŁ

-0.14

ffen

-0.14

anny

-0.14

POSITIVE LOGITS

alla

0.14

auce

0.14

hom

0.14

ÙĬÙĪÙĨ

0.14

grav

0.14

 reve

0.14

ecd

0.14

lon

0.13

washer

0.13

dea

0.13

Activations Density 0.023%

phrases that indicate personal inquiry or actions related to self

No Comments

No Known Activations