INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

viso

-0.19

vb

-0.15

cmc

-0.14

PostBack

-0.14

/xhtml

-0.13

ategories

-0.13

hiba

-0.13

YRO

-0.13

elden

-0.13

lied

-0.13

POSITIVE LOGITS

ÑĥÑĢÐ½

0.15

ESH

0.15

oba

0.14

rica

0.14

exas

0.14

ickle

0.14

Iterator

0.14

 Holdings

0.13

 Schmidt

0.13

TBD

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.