INDEX

Explanations

proper nouns and specific names in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

kowski

-0.15

agus

-0.15

ubat

-0.14

insky

-0.14

mdir

-0.14

dens

-0.14

recht

-0.13

asonic

-0.13

pedia

-0.13

_usec

-0.13

POSITIVE LOGITS

 Rowe

0.14

unf

0.14

 Challenger

0.13

eva

0.13

et

0.13

0.12

 Revision

0.12

ova

0.12

Dit

0.12

Activations Density 0.120%

proper nouns and specific names in a scientific context

No Comments

No Known Activations