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

uet

-0.17

finity

-0.17

umbo

-0.15

ibur

-0.15

iard

-0.15

ette

-0.14

urgy

-0.14

iegel

-0.14

rd

-0.14

enek

-0.14

POSITIVE LOGITS

loquent

0.17

çĢ¬

0.16

Traits

0.15

quirer

0.14

ldb

0.14

.addAll

0.14

 choke

0.14

.EventArgs

0.14

kee

0.13

aits

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.