INDEX

Explanations

numerical values and references related to scientific publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

clave

-0.17

-0.15

hatt

-0.15

-0.14

Å¯r

-0.14

cene

-0.13

ording

-0.13

POSITIVE LOGITS

ÙĪØ§ÙĦ

0.15

Alb

0.15

vik

0.15

 Consent

0.14

vig

0.14

ESC

0.14

.resume

0.14

 Albany

0.14

ESC

0.14

Activations Density 0.055%

numerical values and references related to scientific publications

No Comments

No Known Activations