INDEX

Explanations

words indicating a user's actions or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ath

-0.15

ãĤ¿ãĥ¼

-0.15

atts

-0.15

shire

-0.14

pret

-0.14

 pretend

-0.13

igi

-0.13

kl

-0.13

ihu

-0.12

 Fach

-0.12

POSITIVE LOGITS

.createFrom

0.16

dea

0.15

 Jong

0.14

Insn

0.14

gua

0.14

/DTD

0.14

à¸¸à¸¥

0.14

Î»Î¿Î³Î¯Î±

0.13

andum

0.13

ationToken

0.13

Activations Density 0.075%

words indicating a user's actions or experiences

No Comments

No Known Activations