INDEX

Explanations

sections or chapters in a structured document, often markup or outline elements like parts and requirements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

op

-0.17

assis

-0.16

ãĥ«ãĥĪ

-0.16

Op

-0.14

ple

-0.14

é»Ħ

-0.14

ite

-0.14

no

-0.14

ople

-0.14

owl

-0.14

POSITIVE LOGITS

uyá»ĩt

0.17

Subset

0.15

stad

0.14

ÏĦÎ¹Î¿

0.14

CAA

0.14

Äĩi

0.14

/Instruction

0.13

ìķķ

0.13

erville

0.13

Stride

0.13

Activations Density 0.026%

sections or chapters in a structured document, often markup or outline elements like parts and requirements

No Comments

No Known Activations