INDEX

Explanations

specific references to categories or groupings within various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

inger

-0.16

antan

-0.15

rico

-0.14

æľĹ

-0.14

oland

-0.14

leigh

-0.13

 Ð´ÑĢÑĥÐ³Ð°

-0.13

czy

-0.13

jez

-0.13

eam

-0.13

POSITIVE LOGITS

ãĥĨãĥ«

0.15

0.14

/print

0.14

 UITableViewDelegate

0.14

fet

0.14

orrent

0.14

ikes

0.13

ussen

0.13

ero

0.13

Activations Density 0.051%

specific references to categories or groupings within various contexts

No Comments

No Known Activations