INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ideon

-0.14

court

-0.14

ÐºÐ°Ð²

-0.14

.Emit

-0.14

shan

-0.14

Ð»Ð°Ð³Ð¾Ð´

-0.14

lug

-0.14

ìľ¼

-0.14

 aborted

-0.14

EMPL

-0.14

POSITIVE LOGITS

ettle

0.15

ownik

0.15

omik

0.14

 passe

0.14

EIF

0.14

odesk

0.14

 recep

0.14

mdl

0.14

iaux

0.14

rock

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.