INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

-0.17

acas

-0.15

icz

-0.15

arez

-0.15

-0.14

ă

-0.14

agra

-0.13

orque

-0.13

 Gran

-0.13

[*

-0.13

POSITIVE LOGITS

 pilots

0.14

 guns

0.14

 Sark

0.14

/php

0.14

ensburg

0.14

.truth

0.14

Cli

0.14

Wen

0.13

maz

0.13

gun

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.