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

aci

-0.17

rex

-0.15

px

-0.14

 âĢº

-0.14

 Schmidt

-0.14

ands

-0.14

 moment

-0.14

adj

-0.13

last

-0.13

gt

-0.13

POSITIVE LOGITS

ootball

0.16

_unix

0.15

 Huffman

0.15

 Backbone

0.14

hum

0.14

 Alice

0.14

ften

0.14

iÃ§

0.13

adget

0.13

 sucker

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.