INDEX

Explanations

keywords related to the documentation and reporting of significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

arak

-0.16

 Cage

-0.15

 Pazar

-0.15

noch

-0.15

ç¾½

-0.14

 Loose

-0.14

 sunk

-0.14

 Cant

-0.14

 Rein

-0.14

inen

-0.14

POSITIVE LOGITS

ulator

0.17

otherwise

0.16

eller

0.15

 otherwise

0.15

ominator

0.15

strand

0.15

(&$

0.15

otta

0.14

jabi

0.14

Activations Density 0.148%

keywords related to the documentation and reporting of significant events

No Comments

No Known Activations