INDEX

Explanations

connections or combinations involving the word "and"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

onu

-0.16

erce

-0.15

ivan

-0.15

erialized

-0.14

amo

-0.14

wat

-0.14

unan

-0.14

ef

-0.14

arga

-0.13

zn

-0.13

POSITIVE LOGITS

_simps

0.16

 onBind

0.14

ursed

0.14

uitka

0.14

æ¯

0.14

bright

0.14

void

0.14

OKIE

0.14

 void

0.14

rod

0.14

Activations Density 0.247%

connections or combinations involving the word "and"

No Comments

No Known Activations