INDEX

Explanations

mentions of individuals and their corresponding actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ora

-0.16

ep

-0.15

arrera

-0.14

arker

-0.14

pton

-0.14

istem

-0.14

ÅĤy

-0.14

asley

-0.14

lyn

-0.14

entin

-0.13

POSITIVE LOGITS

ê¶ģ

0.17

llu

0.14

ues

0.14

.metro

0.14

 sour

0.14

$?

0.14

ances

0.14

Ĳ

0.13

 Sour

0.13

folio

0.13

Activations Density 0.020%

mentions of individuals and their corresponding actions or statements

No Comments

No Known Activations