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

 Country

-0.14

rio

-0.14

resco

-0.14

è¿Ļä¹Ī

-0.14

asz

-0.14

evice

-0.13

 behavioural

-0.13

way

-0.13

JI

-0.13

zas

-0.13

POSITIVE LOGITS

-proxy

0.15

antry

0.15

ortex

0.14

Î»Î¿Î½

0.14

/libs

0.14

RuleContext

0.14

èĭ

0.14

 regarding

0.14

allax

0.14

 terminator

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.