INDEX

Explanations

phrases indicating frequency or habitual actions

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

ters

-0.15

atura

-0.15

ura

-0.15

unnel

-0.15

uras

-0.15

 Ð²Ð´ÑĢÑĥÐ³

-0.15

ç¥Ŀ

-0.14

/-

-0.14

ÑĳÑĢ

-0.14

rowsable

-0.14

POSITIVE LOGITS

 Cons

0.17

ulin

0.16

nero

0.14

 cons

0.14

Cons

0.14

oleon

0.14

afa

0.14

Î»Î±Î½

0.13

rics

0.13

Activations Density 0.030%

phrases indicating frequency or habitual actions

No Comments

No Known Activations