INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ean

-0.15

PIO

-0.15

oug

-0.14

iei

-0.14

is

-0.14

Ø§ÙĬØ§

-0.14

sworth

-0.13

ady

-0.13

ekil

-0.13

POSITIVE LOGITS

osal

0.17

bef

0.15

 Sesso

0.15

cosa

0.15

áºŃu

0.15

sat

0.14

_arg

0.14

amaz

0.14

kowski

0.14

ofire

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.