INDEX

Explanations

topics related to the structure and function of various entities or items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

oller

-0.16

 respectively

-0.16

-0.15

 more

-0.15

ever

-0.15

earned

-0.15

 particularly

-0.15

oc

-0.14

POSITIVE LOGITS

 entirety

0.21

ParameterValue

0.19

 Entire

0.18

 entire

0.18

_except

0.16

LLL

0.16

 gÃ³i

0.15

ëį

0.15

PLUS

0.15

æķ´ä¸ª

0.15

Activations Density 0.230%

topics related to the structure and function of various entities or items

No Comments

No Known Activations