INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

·»

-0.15

inea

-0.15

mast

-0.15

opa

-0.14

esen

-0.14

á»Ĳ

-0.14

å¥ĳ

-0.14

Feat

-0.13

 Ð·ÐµÐ¼

-0.13

CLUDING

-0.13

POSITIVE LOGITS

posables

0.15

unta

0.15

 Morrison

0.15

è«

0.15

hone

0.15

imson

0.14

uras

0.14

_Property

0.14

undry

0.14

Haw

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.