INDEX

Explanations

verbs and phrases associated with actions or transformations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

alsa

-0.19

irl

-0.17

ãģĸ

-0.17

hle

-0.15

 Gregg

-0.15

bak

-0.15

íĦ´

-0.15

UMENT

-0.15

rale

-0.15

bben

-0.14

POSITIVE LOGITS

ighthouse

0.15

amage

0.15

 Burton

0.15

bish

0.15

 rein

0.14

Ì£

0.14

ational

0.14

 Iron

0.14

eya

0.14

iesz

0.14

Activations Density 0.018%

verbs and phrases associated with actions or transformations

No Comments

No Known Activations