INDEX

Explanations

references to proteins and protein-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

orget

-0.17

à¸¢

-0.15

/type

-0.15

ible

-0.15

oral

-0.15

IBLE

-0.14

 åł

-0.14

íĦ¸

-0.14

rita

-0.14

acet

-0.14

POSITIVE LOGITS

aceous

0.35

uria

0.26

ase

0.22

ases

0.20

è³ª

0.19

è´¨

0.18

/en

0.18

-rich

0.16

rich

0.16

 Rich

0.15

Activations Density 0.017%

references to proteins and protein-related terminology

No Comments

No Known Activations

references to proteins and protein-related terminology

No Comments

No Known Activations