INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

è°

-0.14

hoff

-0.13

Ł

-0.13

acci

-0.13

ivel

-0.13

=-=-

-0.13

DataSetChanged

-0.13

Scaler

-0.13

sole

-0.13

Tru

-0.13

POSITIVE LOGITS

ÑĨÐ¸Ðº

0.14

anlar

0.14

$($

0.14

licos

0.14

 nest

0.14

iteral

0.13

 otherwise

0.13

issional

0.13

ouse

0.13

 sint

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.