INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

æ°¸ä¹ħ

-0.16

 behaviors

-0.16

linkplain

-0.16

 anyways

-0.15

Quarter

-0.14

aggi

-0.14

/testify

-0.14

 vigor

-0.14

ãģŁãģı

-0.14

 Quarterly

-0.14

POSITIVE LOGITS

 envis

0.16

 blackmail

0.15

 earlier

0.14

SEE

0.14

overn

0.14

Ahead

0.14

 overnight

0.14

 ahead

0.13

 Vlad

0.13

 Venice

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.