INDEX

Explanations

references to proximity and location of places or establishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

typeid

-0.15

wer

-0.14

á»ĳt

-0.14

ãĥ¬ãĥ³

-0.14

ajar

-0.14

Ð»Ð¾Ð¶

-0.14

ije

-0.13

fst

-0.13

ajs

-0.13

atra

-0.13

POSITIVE LOGITS

imler

0.16

/close

0.16

umlu

0.15

 proximity

0.15

anka

0.15

 disponible

0.14

Available

0.14

 disponibles

0.14

buster

0.14

Activations Density 0.012%

references to proximity and location of places or establishments

No Comments

No Known Activations

references to proximity and location of places or establishments

No Comments

No Known Activations