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

linger

-0.15

uren

-0.15

uter

-0.14

ansen

-0.14

Pam

-0.14

AMY

-0.14

Pul

-0.14

 Lans

-0.13

die

-0.13

ose

-0.13

POSITIVE LOGITS

yla

0.16

atisfaction

0.14

.TODO

0.14

 bordel

0.14

anical

0.14

ãĥ³ãĥĩ

0.13

addin

0.13

Hol

0.13

-widgets

0.13

 ÄĳÃ´i

0.13

Activations Density 0.163%

No Comments

No Known Activations