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

ullan

-0.17

UPI

-0.16

é±

-0.16

ityEngine

-0.15

mpar

-0.15

èİ

-0.14

 discrepan

-0.14

ancel

-0.14

ISTA

-0.14

oby

-0.14

POSITIVE LOGITS

 operator

0.17

its

0.16

lays

0.16

 Operator

0.15

operator

0.14

-operator

0.14

longleftrightarrow

0.14

cap

0.14

axter

0.14

Nu

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.