INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

TTY

-0.13

 Vick

-0.13

 deline

-0.13

ROME

-0.12

isos

-0.12

mod

-0.12

 Tento

-0.12

 âĢª

-0.12

ëĿ

-0.12

Council

-0.12

POSITIVE LOGITS

oins

0.16

ipse

0.16

luÅ¾

0.15

aeda

0.15

edla

0.14

oin

0.14

à¸§à¸Ļ

0.14

svc

0.14

Ð¸Ð´ÐµÐ½ÑĤ

0.14

ãģĵãģĿ

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.