INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

bam

-0.15

opsis

-0.14

co

-0.14

store

-0.14

Vak

-0.14

enance

-0.14

lar

-0.13

cur

-0.13

 Enterprises

-0.13

iken

-0.13

POSITIVE LOGITS

 autogenerated

0.15

GraphNode

0.14

HLT

0.14

,$_

0.14

_OBJC

0.14

nout

0.14

.TestTools

0.14

Å¡ov

0.14

 sharedInstance

0.14

anson

0.14

Activations Density 0.020%

No Comments

No Known Activations