INDEX

Explanations

instances of significant events or situations involving changes or actions affecting individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

rzy

-0.18

uat

-0.14

Nam

-0.14

Ð´ÑĢÐµÑģ

-0.14

 Rosenstein

-0.14

dof

-0.13

phis

-0.13

inha

-0.13

imes

-0.13

POSITIVE LOGITS

Scaler

0.18

eler

0.15

ãĥ¼ãĥª

0.14

 Globe

0.14

 earlier

0.14

ulus

0.13

ILT

0.13

_Store

0.13

elen

0.13

else

0.13

Activations Density 0.175%

instances of significant events or situations involving changes or actions affecting individuals or groups

No Comments

No Known Activations