INDEX

Explanations

mentions of specific names or titles associated with entertainment or media

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

Â¯Â¯Â¯Â¯

-0.14

erken

-0.14

acky

-0.14

oreach

-0.14

deaux

-0.14

cheid

-0.14

 Catholic

-0.14

ÑĩÐµ

-0.14

ãĤıãģļ

-0.14

amient

-0.13

POSITIVE LOGITS

igm

0.15

 Masc

0.14

arel

0.14

antes

0.14

inary

0.14

0.13

whe

0.13

ocking

0.13

ooled

0.13

Activations Density 0.004%

mentions of specific names or titles associated with entertainment or media

No Comments

No Known Activations