INDEX

Explanations

references to specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

mon

-0.16

-mon

-0.15

ãĥ³ãĥģ

-0.15

ervoir

-0.14

åı

-0.14

Timing

-0.14

ANDOM

-0.14

ãĥ¼ãĥģ

-0.14

POSITIVE LOGITS

hack

0.17

hod

0.17

eneg

0.16

elier

0.16

Fri

0.16

Mev

0.15

Hack

0.15

kowski

0.15

 dist

0.15

ILT

0.15

Activations Density 0.024%

references to specific years

No Comments

No Known Activations