INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

iglia

-0.23

iae

-0.15

áº

-0.15

NECT

-0.15

oso

-0.14

chant

-0.14

 integ

-0.14

chalk

-0.14

asco

-0.14

ARING

-0.14

POSITIVE LOGITS

iggins

0.15

theon

0.15

jamin

0.14

ëª

0.14

.datas

0.14

ogi

0.14

idir

0.14

attrs

0.14

_malloc

0.13

 Higgins

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.