INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

}\.[

-0.15

ãĤ¸ãĤª

-0.14

dys

-0.14

 Sunderland

-0.14

rink

-0.14

ikk

-0.14

 Advent

-0.13

ÑĤÑĥÑĢÐ°

-0.13

 Hubb

-0.13

irling

-0.13

POSITIVE LOGITS

Bit

0.26

(bit

0.26

bit

0.25

Bit

0.25

plugin

0.24

 plugin

0.24

 Plugin

0.24

Plugin

0.24

_plugin

0.24

/bit

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.