INDEX

Explanations

geographical locations and names of places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Resorts

-0.16

relude

-0.15

EK

-0.14

Agr

-0.14

-eslint

-0.14

ottage

-0.14

 ÑģÐ¿Ð¾ÑĢ

-0.14

 resorts

-0.13

ileged

-0.13

osemite

-0.13

POSITIVE LOGITS

 district

0.18

 area

0.18

[assembly

0.16

-area

0.15

Î¬ÏĤ

0.14

ameda

0.14

iens

0.14

nest

0.14

mium

0.13

 streets

0.13

Activations Density 0.199%

geographical locations and names of places

No Comments

No Known Activations

geographical locations and names of places

No Comments

No Known Activations