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

abo

-0.20

ogan

-0.16

aris

-0.16

 cÃ´t

-0.16

-io

-0.15

uning

-0.15

pta

-0.15

ubat

-0.15

unta

-0.15

rs

-0.15

POSITIVE LOGITS

raphic

0.14

_ARGUMENT

0.13

ãĥĨãĥ«

0.13

[--

0.13

 trench

0.13

 Tobacco

0.13

DONE

0.13

[rand

0.13

_interfaces

0.13

è¡¡

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.