INDEX

Explanations

references to individuals or personal identifiers in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Gall

-0.15

 Woods

-0.14

enso

-0.14

 Westbrook

-0.14

 peer

-0.14

 complement

-0.14

chap

-0.14

amental

-0.13

WO

-0.13

POSITIVE LOGITS

umbo

0.16

FHA

0.14

GetInstance

0.14

ihn

0.14

Ã¤nner

0.14

egg

0.14

 Jarvis

0.14

 konkrÃ©t

0.14

erot

0.14

ucht

0.14

Activations Density 0.001%

references to individuals or personal identifiers in various contexts

No Comments

No Known Activations