INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

verty

-0.17

olla

-0.16

utes

-0.15

 Serif

-0.14

à¤¾à¤²à¤¤

-0.14

hiba

-0.14

icias

-0.13

Ð²Ð°Ð»Ð¸

-0.13

HAV

-0.13

eneg

-0.13

POSITIVE LOGITS

TH

0.15

pj

0.15

#\

0.14

lest

0.14

_annotations

0.14

lord

0.14

 Sung

0.14

kud

0.14

 Passenger

0.14

by

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.