INDEX

Explanations

mentions of the word "cream."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 meille

-0.16

inel

-0.15

çīĻ

-0.15

udi

-0.15

scr

-0.15

uby

-0.14

god

-0.14

akin

-0.14

ãĥ£

-0.14

 preco

-0.13

POSITIVE LOGITS

itan

0.17

sonian

0.16

slideUp

0.15

feld

0.15

IRT

0.14

refix

0.14

iliki

0.14

EIF

0.14

LError

0.14

Ø§Ø²Ø§Øª

0.14

Activations Density 0.005%

mentions of the word "cream."

No Comments

No Known Activations