INDEX

Explanations

references to identities and representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ambi

-0.16

amus

-0.16

æµ¦

-0.15

 Ð§Ð°Ñģ

-0.15

amarin

-0.15

 æ¥Ń

-0.14

ruc

-0.14

pute

-0.14

irit

-0.14

phylum

-0.14

POSITIVE LOGITS

erness

0.15

Os

0.15

 Dome

0.15

Inset

0.14

enburg

0.14

ash

0.14

elho

0.14

 Leadership

0.14

.cache

0.14

ii

0.14

Activations Density 0.046%

references to identities and representation

No Comments

No Known Activations