INDEX

Explanations

references to specific locations and communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

sak

-0.17

 REGION

-0.16

 Province

-0.16

Province

-0.15

Region

-0.15

 Landscape

-0.15

 rÃ©gion

-0.15

 Region

-0.14

Regional

-0.14

 Provincial

-0.14

POSITIVE LOGITS

osto

0.15

ignet

0.15

hs

0.15

BoundingBox

0.14

 Hague

0.14

åŃĹ

0.14

cken

0.13

/Set

0.13

oli

0.13

Activations Density 0.167%

references to specific locations and communities

No Comments

No Known Activations