INDEX

Explanations

references to threats and acts of violence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

andle

-0.16

ught

-0.16

ought

-0.16

eck

-0.15

ece

-0.15

 dear

-0.15

reck

-0.14

TJ

-0.14

ese

-0.14

 defining

-0.14

POSITIVE LOGITS

illos

0.14

 Brewer

0.14

ç»Ī

0.14

uyo

0.14

-Ð»Ð¸

0.14

çµĤ

0.14

 Eaton

0.14

dirs

0.14

gateway

0.14

ëģ

0.13

Activations Density 0.411%

references to threats and acts of violence

No Comments

No Known Activations