INDEX

Explanations

variations of the word "bl," indicating a focus on references to "blue."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Ä±lÄ±Ã§

-0.16

_DUMP

-0.15

 Gate

-0.15

neau

-0.15

lasÄ±

-0.15

Å¡ti

-0.14

leston

-0.14

AreaView

-0.14

Ä±ÅŁÄ±k

-0.14

lopen

-0.14

POSITIVE LOGITS

ues

0.33

inded

0.32

ended

0.32

onde

0.31

own

0.31

ame

0.31

azing

0.31

urred

0.31

owing

0.30

ow

0.30

Activations Density 0.017%

variations of the word "bl," indicating a focus on references to "blue."

No Comments

No Known Activations