INDEX

Explanations

relationships involving loyalty and betrayal

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

leftright

-0.20

vara

-0.16

ingles

-0.16

IFn

-0.15

liers

-0.15

ael

-0.15

nga

-0.15

ÙĪØ±Ø¯

-0.15

ovsky

-0.14

POSITIVE LOGITS

ÐµÑı

0.15

mt

0.14

imir

0.14

hay

0.14

embr

0.14

Pav

0.14

 Patriot

0.14

ance

0.13

ius

0.13

 Pathfinder

0.13

Activations Density 0.045%

relationships involving loyalty and betrayal

No Comments

No Known Activations