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

GuidId

-0.15

æĲľ

-0.15

.yahoo

-0.15

-lfs

-0.15

ERA

-0.15

ãĥĪãĥª

-0.14

wat

-0.14

apon

-0.14

ÐĽÐŀ

-0.14

InitStruct

-0.14

POSITIVE LOGITS

chter

0.15

edList

0.15

Smy

0.15

Vi

0.14

 native

0.14

ambre

0.14

ÙĩÙĨ

0.14

igli

0.14

MMdd

0.14

onec

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.