INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

/Dk

-0.17

ÏĨÎ±

-0.16

uar

-0.15

ä¿Ŀ

-0.15

erg

-0.15

vard

-0.14

rew

-0.14

illa

-0.14

itt

-0.14

POSITIVE LOGITS

odox

0.15

aggable

0.15

opensource

0.15

emey

0.15

SYM

0.15

.ToShort

0.15

cobra

0.14

VIS

0.14

vÄĽt

0.14

bsolute

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.