INDEX

Explanations

instances of the word "first" and indicators of prominence or ranking

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

igg

-0.17

owi

-0.16

coli

-0.14

zev

-0.14

 Helm

-0.14

apper

-0.14

rq

-0.14

rah

-0.14

annon

-0.14

POSITIVE LOGITS

cname

0.14

indle

0.14

kuk

0.14

Signing

0.14

mai

0.14

composite

0.14

Hud

0.14

uda

0.14

èı

0.13

Ð»Ñİ

0.13

Activations Density 0.084%

instances of the word "first" and indicators of prominence or ranking

No Comments

No Known Activations