INDEX

Explanations

quotations or dialogue 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ÐµÐ»ÐµÐ½

-0.15

odef

-0.15

Bindable

-0.15

 ((__

-0.14

Ã¹a

-0.14

ÑĥÑĢÑĥ

-0.14

eki

-0.13

ardin

-0.13

Ä°Åŀ

-0.13

retim

-0.13

POSITIVE LOGITS

pending

0.16

hy

0.15

 pending

0.15

itus

0.15

exe

0.15

0.14

plural

0.14

itan

0.14

oeff

0.14

pic

0.14

Activations Density 0.000%

quotations or dialogue within the text

No Comments

No Known Activations