INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ouble

-0.16

 Emer

-0.15

 Vanderbilt

-0.15

 Bert

-0.15

Eb

-0.15

-0.13

Sad

-0.13

hani

-0.13

Map

-0.13

del

-0.13

POSITIVE LOGITS

İ

0.16

TestMethod

0.15

Od

0.15

ICAST

0.15

OfType

0.14

bris

0.14

izr

0.14

DRV

0.14

iag

0.14

jh

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.