INDEX

Explanations

specific punctuation marks and tokens indicating choices or decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

enge

-0.16

ÐµÐ³Ð¾ÑĢ

-0.16

ajar

-0.16

 darn

-0.15

ataka

-0.15

ÑĤÐ¾ÑĦ

-0.14

ãĥ¬ãĥĥãĥĪ

-0.14

 Systems

-0.14

ilim

-0.14

systems

-0.14

POSITIVE LOGITS

alc

0.16

ìĶ¨

0.14

elli

0.14

ulus

0.14

ÑģÑĥ

0.14

usp

0.14

anzi

0.13

ieten

0.13

ç»ı

0.13

Activations Density 0.000%

specific punctuation marks and tokens indicating choices or decisions

No Comments

No Known Activations