INDEX

Explanations

references to live performances and shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

istry

-0.19

ovsky

-0.15

se

-0.14

ly

-0.14

ocus

-0.14

umpt

-0.14

ç¼

-0.14

ious

-0.13

owski

-0.13

POSITIVE LOGITS

ucht

0.16

âĸĪâĸĪ

0.14

ationToken

0.14

 providedIn

0.14

esk

0.14

$__

0.14

toupper

0.13

_TIMES

0.13

 recru

0.13

 QuáºŃn

0.13

Activations Density 0.023%

references to live performances and shows

No Comments

No Known Activations