INDEX

Explanations

numerical and measurement-related information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ä¸ĭåİ»

-0.16

 susp

-0.15

noch

-0.15

celik

-0.15

Ú¯ÙĦ

-0.14

 Concord

-0.14

ActionCreators

-0.14

evi

-0.14

 helicopt

-0.14

POSITIVE LOGITS

iem

0.17

uttle

0.15

roat

0.15

Regressor

0.14

itory

0.14

 amateur

0.14

à§į

0.14

sp

0.14

gre

0.13

Nib

0.13

Activations Density 0.015%

numerical and measurement-related information

No Comments

No Known Activations