INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

äº«

-0.14

#Region

-0.14

FX

-0.14

ppers

-0.13

 Probe

-0.13

 complied

-0.13

å¶

-0.13

_probe

-0.13

ÏĮ

-0.13

 Prof

-0.13

POSITIVE LOGITS

.literal

0.16

 GrÃ¼

0.16

.Mapping

0.14

igy

0.13

eld

0.13

_lineno

0.13

 literal

0.13

 loud

0.13

mail

0.13

 Loud

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.