INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

_hdl

-0.18

iba

-0.15

 Arbeit

-0.14

.xhtml

-0.14

omnia

-0.14

.xz

-0.14

.metro

-0.13

noch

-0.13

apl

-0.13

 ::::::::

-0.13

POSITIVE LOGITS

 viral

0.18

 sort

0.18

vir

0.18

 kind

0.17

 classic

0.16

0.15

Vir

0.15

 perhaps

0.14

_EMIT

0.14

 kinds

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.