INDEX

Explanations

references to alternatives or additional options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

BuilderInterface

-0.16

ÑĩÐ¸Ðº

-0.15

ÏĦÎ¶

-0.15

ering

-0.15

ned

-0.14

zimmer

-0.14

imals

-0.14

 itself

-0.14

 himself

-0.14

-set

-0.14

POSITIVE LOGITS

 parts

0.16

0.15

 equally

0.15

-than

0.14

Äįe

0.14

 nhau

0.14

azen

0.14

ewise

0.14

/new

0.14

 than

0.14

Activations Density 0.141%

references to alternatives or additional options

No Comments

No Known Activations

references to alternatives or additional options

No Comments

No Known Activations