INDEX

Explanations

concepts or discussions related to specific subjects or issues

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

ptal

-0.14

tae

-0.14

 Kelly

-0.14

(åľŁ

-0.14

arehouse

-0.13

ateway

-0.13

entina

-0.13

eÅŁ

-0.13

odox

-0.13

 addCriterion

-0.13

POSITIVE LOGITS

 matter

0.17

eldorf

0.16

ilis

0.15

ÙĤØ±

0.15

ahat

0.15

Reached

0.14

kowski

0.14

chron

0.14

avor

0.14

 Roth

0.14

Activations Density 0.146%

concepts or discussions related to specific subjects or issues

No Comments

No Known Activations