INDEX

Explanations

references to living or residing in a place

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

arth

-0.15

PELL

-0.15

agement

-0.14

undan

-0.14

 turb

-0.14

ezi

-0.14

Town

-0.13

"go

-0.13

riba

-0.13

POSITIVE LOGITS

 Newsp

0.17

 Newspaper

0.16

 ÑģÐ¿ÑĢÐ°Ð²

0.14

 GOODS

0.14

etter

0.14

ports

0.14

ActionCreators

0.13

LIK

0.13

 switches

0.13

ersion

0.13

Activations Density 0.008%

references to living or residing in a place

No Comments

No Known Activations