INDEX

Explanations

website references and bibliographic entries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

itness

-0.17

ennie

-0.14

uelle

-0.14

ÙĪÙĬÙĥ

-0.14

avicon

-0.13

leck

-0.13

fat

-0.13

PLICATION

-0.13

pone

-0.13

.webkit

-0.13

POSITIVE LOGITS

.mixin

0.15

lemn

0.15

0.14

unexpected

0.14

anj

0.14

RID

0.13

IDEO

0.13

Activations Density 0.015%

website references and bibliographic entries

No Comments

No Known Activations