INDEX

Explanations

references to possessive pronouns and personal context in relation to problems or questions posed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

-desktop

-0.15

zano

-0.15

opak

-0.15

gran

-0.15

presence

-0.15

criptor

-0.14

alone

-0.14

Aspect

-0.14

ni

-0.14

-placeholder

-0.14

POSITIVE LOGITS

0.16

 custom

0.16

 Farrell

0.16

 target

0.15

 desired

0.15

faces

0.15

0.14

 tact

0.14

 protocol

0.14

 favorite

0.14

Activations Density 0.083%

references to possessive pronouns and personal context in relation to problems or questions posed

No Comments

No Known Activations