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

reon

-0.16

oya

-0.15

¯u

-0.14

ÐĴÑĤ

-0.14

lington

-0.14

//{{

-0.14

ÑģÑĮ

-0.14

brick

-0.13

_drawer

-0.13

/Area

-0.13

POSITIVE LOGITS

ãĥ¼ãĥį

0.16

udent

0.14

Ra

0.14

all

0.14

Rah

0.14

dh

0.14

Nat

0.14

axon

0.13

nat

0.13

sou

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.