INDEX

Explanations

terms and phrases related to remedies and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 erst

-0.17

/GPL

-0.17

 Renaissance

-0.16

ahoma

-0.15

rych

-0.15

 cigaret

-0.15

 envis

-0.15

 journalistic

-0.15

 Reconstruction

-0.14

 psychic

-0.14

POSITIVE LOGITS

 subs

0.19

Å

0.17

 insulated

0.17

 âŁ¨

0.16

 Female

0.15

&D

0.15

Å

0.15

 comp

0.15

âŁ

0.14

 domest

0.14

Activations Density 0.450%

terms and phrases related to remedies and their effects

No Comments

No Known Activations