INDEX

Explanations

references to formal or official entries and agreements

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ching

-0.17

roller

-0.16

ski

-0.15

iki

-0.15

Ã£ng

-0.14

 Roller

-0.14

omi

-0.14

 Mess

-0.14

âĢ¦↵↵↵

-0.14

ly

-0.14

POSITIVE LOGITS

prising

0.17

Å¼y

0.17

prises

0.16

íĥľ

0.14

itol

0.14

umen

0.14

HU

0.14

ModelProperty

0.14

etical

0.14

stral

0.13

Activations Density 0.015%

references to formal or official entries and agreements

No Comments

No Known Activations