INDEX

Explanations

elements related to notable publications or media, especially surrounding artistic works and treatments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

itives

-0.14

NSK

-0.14

Ä±ndÄ±r

-0.14

liÅ¡

-0.14

 individuals

-0.13

 Tits

-0.13

omu

-0.13

_nsec

-0.13

ffen

-0.13

_CONN

-0.13

POSITIVE LOGITS

hol

0.15

Hol

0.15

anol

0.15

 Bols

0.14

Ã¤l

0.14

-ÑĤ

0.14

bol

0.14

abol

0.14

odef

0.14

Bol

0.13

Activations Density 0.055%

elements related to notable publications or media, especially surrounding artistic works and treatments

No Comments

No Known Activations