INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

lixir

-0.15

Å¾el

-0.15

odu

-0.15

plx

-0.14

 dequeueReusableCellWithIdentifier

-0.14

.metro

-0.14

azzi

-0.14

rchive

-0.14

 Fucking

-0.14

kontakte

-0.14

POSITIVE LOGITS

 èį

0.16

HIR

0.15

 somewhere

0.15

yk

0.15

 alongside

0.14

mic

0.14

Mic

0.14

 figures

0.14

 simple

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.