INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

cec

-0.16

vt

-0.16

ãĥ³ãĥĪ

-0.16

cess

-0.15

rend

-0.15

FIXME

-0.15

 Thing

-0.14

ãĥĥãĥģ

-0.14

 Pearl

-0.14

.ensure

-0.14

POSITIVE LOGITS

-END

0.16

 Latter

0.14

.scalablytyped

0.14

å¤«

0.14

edb

0.14

 Äįe

0.14

_utilities

0.14

Î¼Î¹Ïĥ

0.13

oux

0.13

;br

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.