INDEX

Explanations

terms related to safety regulations and technical failures

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

gratis

-0.17

pii

-0.15

koa

-0.15

éĺµ

-0.14

lescope

-0.14

bian

-0.14

uros

-0.14

ayÄ±m

-0.14

avian

-0.14

éĻ£

-0.13

POSITIVE LOGITS

essler

0.16

ormal

0.16

 condition

0.15

Par

0.14

 Horton

0.14

Abb

0.14

paces

0.14

Activations Density 0.032%

terms related to safety regulations and technical failures

No Comments

No Known Activations