INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

razier

-0.17

 Trafford

-0.16

cket

-0.15

letal

-0.14

 Whilst

-0.14

quiv

-0.14

 Marr

-0.14

Ð»ÑıÑħ

-0.14

orra

-0.14

errs

-0.14

POSITIVE LOGITS

0.16

jin

0.15

 rewards

0.15

uba

0.15

Ro

0.15

0.14

matter

0.14

-trigger

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.