INDEX

Explanations

contractions and possessive forms used in the context of place names or locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

elden

-0.16

eday

-0.15

Ã¼ns

-0.15

braco

-0.15

elly

-0.15

pell

-0.14

ãģĭãĤĭ

-0.14

*******************************************************************************/↵

-0.14

lam

-0.14

anlar

-0.14

POSITIVE LOGITS

ivation

0.16

umph

0.16

icari

0.16

onen

0.15

 gateway

0.15

bib

0.15

CLU

0.15

logen

0.14

 Rivers

0.14

orro

0.14

Activations Density 0.004%

contractions and possessive forms used in the context of place names or locations

No Comments

No Known Activations