INDEX

Explanations

terms related to physical health and exercise

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

Î²Î¬

-0.17

uales

-0.15

 estates

-0.14

 Action

-0.14

robat

-0.13

evi

-0.13

æĵ

-0.13

 alphabetical

-0.13

vak

-0.13

POSITIVE LOGITS

 training

0.18

 Training

0.17

_Lean

0.15

ilter

0.15

Training

0.15

 Coaching

0.15

elps

0.15

Ð´Ð°Ð½

0.15

ç

0.15

stride

0.15

Activations Density 0.082%

terms related to physical health and exercise

No Comments

No Known Activations