INDEX

Explanations

nouns that denote professions or roles with notable achievements or status

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

 Evening

-0.15

 seedu

-0.15

tu

-0.14

ÅĽli

-0.14

-await

-0.14

arro

-0.13

 nearby

-0.13

 æ®

-0.13

ewise

-0.13

è²©

-0.13

POSITIVE LOGITS

let

0.16

ocker

0.15

-turned

0.15

bourg

0.15

 whose

0.15

sembl

0.14

ostel

0.14

ctic

0.14

OTE

0.14

oste

0.14

Activations Density 0.057%

nouns that denote professions or roles with notable achievements or status

No Comments

No Known Activations