INDEX

Explanations

references to educational experiences and transitions

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

 Andr

-0.16

weg

-0.16

 balk

-0.15

 Thornton

-0.15

ewan

-0.15

inou

-0.15

unar

-0.15

 Solic

-0.14

 ÏĥÏįÎ½

-0.14

entar

-0.14

POSITIVE LOGITS

ascript

0.16

Ńå·ŀ

0.15

 pope

0.14

 cellFor

0.14

nun

0.13

ayar

0.13

 é«

0.13

ÐµÐºÐ¾

0.13

 Ø¹Ø¯

0.13

é¡µ

0.13

Activations Density 0.069%

references to educational experiences and transitions

No Comments

No Known Activations