INDEX

Explanations

references to email subscriptions and inbox notifications

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

mez

-0.16

angelo

-0.15

ÏīÎ½Î±

-0.14

udeau

-0.14

enÃ¡

-0.14

ugins

-0.13

flt

-0.13

Å¡ku

-0.13

bÃŃ

-0.13

ÑģÑĤÐ²ÐµÐ½

-0.13

POSITIVE LOGITS

nist

0.15

 Moff

0.15

roj

0.14

DonaldTrump

0.14

spark

0.14

 Guil

0.13

ãĥ«ãĥķ

0.13

agg

0.13

resi

0.13

eter

0.13

Activations Density 0.003%

references to email subscriptions and inbox notifications

No Comments

No Known Activations