INDEX

Explanations

punctuation and formatting elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

trap

-0.14

Î½Î¹

-0.14

isia

-0.14

tay

-0.14

byn

-0.13

 Î£Ïį

-0.13

vier

-0.13

iban

-0.13

oss

-0.13

uml

-0.13

POSITIVE LOGITS

 toJSON

0.15

prung

0.14

ouston

0.14

_SAMPLES

0.13

fillType

0.13

.Companion

0.13

aura

0.13

CompatActivity

0.13

_warnings

0.13

Ð°ÑĤÐ¾Ð²

0.13

Activations Density 0.331%

punctuation and formatting elements

No Comments

No Known Activations