INDEX

Explanations

titles of films or media referenced within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

imeline

-0.19

desired

-0.16

 desired

-0.15

åļ

-0.15

oka

-0.14

uw

-0.14

tery

-0.14

forms

-0.13

 active

-0.13

Registers

-0.13

POSITIVE LOGITS

Performance

0.17

vant

0.17

 Performance

0.17

HF

0.17

 awards

0.16

OSC

0.15

HUD

0.15

 optarg

0.15

 PERFORMANCE

0.15

performance

0.15

Activations Density 0.092%

titles of films or media referenced within the text

No Comments

No Known Activations