INDEX

Explanations

details and recognized individuals associated with specific events or accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

/jav

-0.18

anzi

-0.17

legg

-0.17

lator

-0.16

å¼ĥ

-0.15

EMA

-0.15

ANEL

-0.15

ovice

-0.15

lda

-0.15

/Dk

-0.14

POSITIVE LOGITS

0.18

0.16

0.14

 Orlando

0.14

 Eric

0.14

 Tyler

0.14

 Sean

0.14

uzu

0.14

 Travis

0.14

Activations Density 0.356%

details and recognized individuals associated with specific events or accomplishments

No Comments

No Known Activations