INDEX

Explanations

punctuation marks and their surrounding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ibold

-0.16

anton

-0.15

ãĥģãĥ¥

-0.15

Ð»Ð°Ð·

-0.14

ãĥªãĤ«

-0.14

 tune

-0.14

inea

-0.14

umber

-0.14

fone

-0.14

POSITIVE LOGITS

 æŃ¦

0.15

uil

0.15

æĮĻ

0.14

wear

0.14

mul

0.14

nda

0.14

_skb

0.14

DG

0.14

primitive

0.14

DG

0.13

Activations Density 0.002%

punctuation marks and their surrounding contexts

No Comments

No Known Activations