INDEX

Explanations

instructions and descriptions related to various activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 ahead

-0.15

ht

-0.15

pac

-0.14

 Alien

-0.13

 circ

-0.13

pul

-0.13

pac

-0.13

 Tradition

-0.13

POSITIVE LOGITS

 indoor

0.91

 indoors

0.85

 outdoor

0.83

 Indoor

0.81

 outdoors

0.75

Outdoor

0.71

 Outdoor

0.71

indo

0.56

 Indo

0.51

å®¤

0.35

Activations Density 0.399%

instructions and descriptions related to various activities

No Comments

No Known Activations