INDEX

Explanations

phrases indicating actions or processes that involve handling expectations or conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

iden

-0.18

occo

-0.15

 particular

-0.15

 Neutral

-0.15

 neutral

-0.15

uld

-0.14

nel

-0.14

hed

-0.14

Neutral

-0.14

ertain

-0.13

POSITIVE LOGITS

adla

0.18

ething

0.17

odyn

0.16

0.15

ops

0.15

xfa

0.15

ody

0.14

_NATIVE

0.14

elu

0.14

Activations Density 0.003%

phrases indicating actions or processes that involve handling expectations or conditions

No Comments

No Known Activations