INDEX

Explanations

phrases related to cookie consent and privacy policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 subsystem

-0.17

ichel

-0.15

dictions

-0.15

ertino

-0.14

ãĥĨãĥ«

-0.14

_raises

-0.14

rippling

-0.14

 Stake

-0.13

istro

-0.13

erti

-0.13

POSITIVE LOGITS

unc

0.17

 Dark

0.15

oby

0.15

 dark

0.15

Unc

0.14

UNC

0.14

arl

0.14

 swingers

0.14

hab

0.14

 DARK

0.14

Activations Density 0.022%

phrases related to cookie consent and privacy policies

No Comments

No Known Activations