INDEX

Explanations

references to numerical identifiers and official registrations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

bog

-0.15

 ç¶

-0.15

 strain

-0.14

ElementsByTagName

-0.14

 melting

-0.14

ÏģÎº

-0.14

 Norm

-0.14

olumes

-0.13

DEPTH

-0.13

engkap

-0.13

POSITIVE LOGITS

iture

0.16

Ð°ÑĤÑĥ

0.15

udent

0.15

åı·

0.15

ç¢¼

0.15

çłģ

0.15

isci

0.14

arity

0.14

zav

0.14

Activations Density 0.217%

references to numerical identifiers and official registrations

No Comments

No Known Activations