INDEX

Explanations

the occurrence of the word "nearby" and related references to proximity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

chio

-0.16

itori

-0.16

worthy

-0.15

æ°

-0.15

å©Ĩ

-0.14

iphy

-0.14

 egret

-0.14

anch

-0.14

udden

-0.14

ccione

-0.14

POSITIVE LOGITS

/on

0.16

/local

0.15

OSH

0.14

shore

0.14

 Lund

0.14

0.13

 nearby

0.13

osh

0.13

 Tale

0.13

Activations Density 0.015%

the occurrence of the word "nearby" and related references to proximity

No Comments

No Known Activations