INDEX

Explanations

instances of personal identity and relationships 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 @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 abandoned

-0.14

sÄ±z

-0.13

enti

-0.13

 fiber

-0.13

ÙĪØ§Ùĩ

-0.13

 unrecognized

-0.13

ollen

-0.13

POSITIVE LOGITS

Nar

0.16

 remot

0.15

antity

0.15

Ã¡u

0.14

UNT

0.14

OfWork

0.14

peg

0.14

 emiss

0.14

ä¼łå¥ĩ

0.14

elop

0.14

Activations Density 0.329%

instances of personal identity and relationships in various contexts

No Comments

No Known Activations