INDEX

Explanations

references to specific individuals and organizations related to media events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

PreferredSize

-0.15

 headphone

-0.14

gre

-0.14

ritel

-0.14

izards

-0.13

cia

-0.13

lew

-0.13

herits

-0.13

Forever

-0.13

asant

-0.13

POSITIVE LOGITS

UTTON

0.17

_shortcode

0.15

commons

0.13

ENTRY

0.13

à¥ĩà¤¯

0.13

lya

0.13

IGENCE

0.13

Activations Density 0.009%

references to specific individuals and organizations related to media events

No Comments

No Known Activations