INDEX

Explanations

mentions of specific geographic regions or areas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

-0.18

speaker

-0.16

ress

-0.16

wow

-0.15

uten

-0.15

ÐµÑı

-0.15

aign

-0.15

ç®±

-0.15

sit

-0.14

pts

-0.14

POSITIVE LOGITS

ally

0.48

ality

0.34

als

0.33

ALLY

0.30

/local

0.28

naire

0.26

/global

0.26

naires

0.26

wide

0.25

-wide

0.25

Activations Density 0.027%

mentions of specific geographic regions or areas

No Comments

No Known Activations