INDEX

Explanations

references to retrieved documents or information sources

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

èĿ

-0.17

ogl

-0.15

side

-0.14

ser

-0.14

ser

-0.14

ach

-0.14

eka

-0.14

ette

-0.14

Ì£

-0.14

array

-0.13

POSITIVE LOGITS

omm

0.17

ustos

0.15

^K

0.15

Https

0.15

aeda

0.15

uhl

0.14

 Mend

0.14

amak

0.14

ogue

0.14

Mol

0.14

Activations Density 0.006%

references to retrieved documents or information sources

No Comments

No Known Activations