INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ene

-0.16

anke

-0.15

inion

-0.15

ANGO

-0.14

jal

-0.14

çļĦæīĭ

-0.14

à¤Łà¤ķ

-0.14

iolet

-0.14

otope

-0.14

anager

-0.14

POSITIVE LOGITS

stadt

0.15

Äł

0.15

.dsl

0.15

owie

0.15

/fs

0.14

 quiet

0.14

 outdoor

0.13

.metro

0.13

istik

0.13

 indoor

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.