INDEX

Explanations

geographic locations and related descriptors

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

gne

-0.17

ksam

-0.17

.Completed

-0.16

 Township

-0.15

atori

-0.15

æĭ³

-0.15

inition

-0.15

Gan

-0.15

.IsMatch

-0.15

dac

-0.14

POSITIVE LOGITS

 Kentucky

0.49

KY

0.43

 Louisville

0.39

KY

0.38

Ky

0.35

Kent

0.34

 Lexington

0.32

ky

0.31

Ky

0.31

 Derby

0.27

Activations Density 0.082%

geographic locations and related descriptors

No Comments

No Known Activations