INDEX

Explanations

conjunctions and linking words that connect ideas or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

mie

-0.14

isan

-0.14

PPP

-0.14

ÃŃny

-0.13

 INCIDENTAL

-0.13

Ã³s

-0.13

isi

-0.13

AIL

-0.13

ventus

-0.13

ç½²

-0.13

POSITIVE LOGITS

erra

0.17

ossier

0.15

istar

0.14

/of

0.14

ugen

0.14

eraÃ§Ã£o

0.14

_RS

0.14

ilden

0.14

gers

0.13

itten

0.13

Activations Density 0.200%

conjunctions and linking words that connect ideas or phrases

No Comments

No Known Activations