INDEX

Explanations

references to leadership positions or titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

immers

-0.17

llib

-0.16

tical

-0.15

antz

-0.14

è´¨

-0.14

anch

-0.14

åŃ£

-0.14

anke

-0.14

ãĤ£

-0.14

DEX

-0.14

POSITIVE LOGITS

ëª

0.17

stery

0.17

dom

0.16

 Ð¾Ð±ÑĢÐ°Ð·Ð¾Ð¼

0.15

-of

0.15

/latest

0.14

zeitig

0.14

enary

0.14

 Loved

0.14

.nih

0.14

Activations Density 0.026%

references to leadership positions or titles

No Comments

No Known Activations