INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

utsch

-0.19

nad

-0.16

é¬¼

-0.15

Cad

-0.15

cid

-0.14

ENG

-0.14

iac

-0.13

arna

-0.13

stash

-0.13

POSITIVE LOGITS

 fucking

0.18

 fuck

0.16

 Fuck

0.16

å¡ļ

0.15

 FUCK

0.14

CString

0.14

icho

0.14

usercontent

0.14

Fuck

0.14

 Fucking

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.