INDEX

Explanations

phrases related to user consent and data usage policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

avor

-0.19

 Instructions

-0.14

Fle

-0.14

Î¼Î¹Ïĥ

-0.13

ripe

-0.13

isu

-0.13

urd

-0.13

 inversion

-0.13

Hat

-0.13

edio

-0.13

POSITIVE LOGITS

 Continued

0.17

continued

0.16

 continued

0.16

agua

0.15

_fwd

0.15

DeltaTime

0.15

achi

0.15

 Fifth

0.15

 toch

0.14

 ///<

0.14

Activations Density 0.011%

phrases related to user consent and data usage policies

No Comments

No Known Activations