INDEX

Explanations

terms related to props and property in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

erk

-0.16

ë¦¬ìĸ´

-0.15

ayan

-0.14

contr

-0.14

ered

-0.14

boj

-0.14

istrat

-0.14

catid

-0.14

POSITIVE LOGITS

_LEG

0.15

dzi

0.14

Å

0.14

eties

0.14

ofil

0.14

 Prop

0.14

ahi

0.14

sel

0.14

 zoekt

0.14

dal

0.13

Activations Density 0.032%

terms related to props and property in various contexts

No Comments

No Known Activations