INDEX

Explanations

terms related to fireplaces and fire-related features

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

Ãłu

-0.15

ModelProperty

-0.15

HIR

-0.15

anguard

-0.15

rous

-0.15

ÃŃna

-0.15

apore

-0.14

áº§y

-0.14

keley

-0.14

dur

-0.14

POSITIVE LOGITS

çģ°

0.18

0.17

elman

0.14

 Schiff

0.14

cheon

0.14

ulates

0.14

asn

0.14

 Marsh

0.14

0.13

ixa

0.13

Activations Density 0.008%

terms related to fireplaces and fire-related features

No Comments

No Known Activations