INDEX

Explanations

expressions of existence or definitions regarding entities or subjects

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

orr

-0.18

ãĥ¼ãĥĭ

-0.16

yo

-0.16

izz

-0.15

esi

-0.15

holder

-0.14

 pipeline

-0.14

zo

-0.14

 disreg

-0.14

agara

-0.14

POSITIVE LOGITS

enschaft

0.20

/is

0.16

PHA

0.16

emek

0.14

 gÃ¼

0.14

fits

0.14

eken

0.14

INESS

0.14

haar

0.14

erness

0.14

Activations Density 0.014%

expressions of existence or definitions regarding entities or subjects

No Comments

No Known Activations