INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ayo

-0.15

mrt

-0.15

enton

-0.15

IFA

-0.15

outers

-0.14

lich

-0.14

drs

-0.14

lum

-0.14

ch

-0.14

ÙĪØ±

-0.14

POSITIVE LOGITS

interop

0.16

0.15

rÃ³

0.15

iaux

0.14

ERA

0.14

era

0.14

ertz

0.14

pb

0.14

reira

0.14

czy

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.