INDEX

Explanations

spatial references and locations within a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

åºŃ

-0.18

åł¡

-0.17

anut

-0.16

åº§

-0.16

avery

-0.14

ajas

-0.14

ynch

-0.14

eniable

-0.14

 ConnectionState

-0.14

POSITIVE LOGITS

Weg

0.16

ECTOR

0.15

 area

0.14

lep

0.14

Whe

0.14

((-

0.13

McG

0.13

 Armstrong

0.13

 Career

0.13

_perms

0.13

Activations Density 0.393%

spatial references and locations within a narrative

No Comments

No Known Activations