INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

nig

-0.14

IGIN

-0.14

è³ª

-0.13

ãģ£ãģı

-0.13

é¨

-0.13

ph

-0.13

ìĬ¤íĬ¸

-0.13

COMPARE

-0.12

Wiki

-0.12

fÃ¼g

-0.12

POSITIVE LOGITS

olley

0.18

 Clay

0.16

Fol

0.15

éĶĢ

0.15

 Segment

0.15

_segment

0.14

 listeners

0.14

opot

0.14

incare

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.