INDEX

Explanations

references to conditional scenarios and potential consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

IW

-0.15

ĶåĽŀ

-0.14

ovah

-0.14

ä»ģ

-0.14

anchors

-0.14

 Vice

-0.14

Vet

-0.14

áº¿n

-0.14

tan

-0.14

lobal

-0.14

POSITIVE LOGITS

.www

0.17

 bÃ©

0.16

Ð¾ÑĢÐ°Ð·

0.15

0.14

oultry

0.14

 Classe

0.14

ë¶Ģ

0.14

0.13

wart

0.13

Activations Density 0.027%

references to conditional scenarios and potential consequences

No Comments

No Known Activations