INDEX

Explanations

the presence of specific proper nouns and important terms related to events or notable subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

çıŃ

-0.15

hardt

-0.15

æĺĵ

-0.15

å¾ĭ

-0.15

 dors

-0.15

rate

-0.15

odia

-0.14

.soft

-0.14

owel

-0.14

_userdata

-0.14

POSITIVE LOGITS

ays

0.19

åĽ

0.16

ashi

0.16

roz

0.16

 Cocktail

0.16

alles

0.15

ruba

0.15

Gin

0.15

erc

0.14

DataStream

0.14

Activations Density 0.016%

the presence of specific proper nouns and important terms related to events or notable subjects

No Comments

No Known Activations