INDEX

Explanations

references to notable or significant projects and creative works

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

eo

-0.18

inson

-0.17

iesta

-0.15

icari

-0.15

linger

-0.14

kuk

-0.14

Misc

-0.14

dit

-0.13

uled

-0.13

piar

-0.13

POSITIVE LOGITS

 Bast

0.15

Ĺ

0.15

ÙĩØ±Ùĩ

0.14

äººãģ¯

0.14

arme

0.13

 apart

0.13

 Bened

0.13

.glide

0.13

brace

0.13

 named

0.13

Activations Density 0.121%

references to notable or significant projects and creative works

No Comments

No Known Activations