INDEX

Explanations

references to actions or activities involving passage through or from locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

inci

-0.17

cka

-0.16

prech

-0.15

vak

-0.15

Ð²Ð¾Ñİ

-0.15

ITUDE

-0.14

ifr

-0.14

íħ

-0.14

aub

-0.14

ÙĪÙĨ

-0.13

POSITIVE LOGITS

ationToken

0.15

zew

0.15

achen

0.15

 Consider

0.14

reb

0.14

 considered

0.14

acz

0.14

erras

0.14

fleet

0.13

ession

0.13

Activations Density 0.009%

references to actions or activities involving passage through or from locations

No Comments

No Known Activations