INDEX

Explanations

information related to structured timeframes and cycles, particularly in formalized contexts like trials or programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Jer

-0.18

Î³Î¿Ïį

-0.17

olit

-0.17

 lasted

-0.16

 lasts

-0.16

 Duration

-0.16

 lasting

-0.16

 overnight

-0.15

 short

-0.15

ogl

-0.15

POSITIVE LOGITS

 Cummings

0.16

ogs

0.15

jay

0.15

uti

0.15

Ð°Ð½Ð¾

0.15

çıŃ

0.14

 ending

0.14

è¾Ľ

0.14

rien

0.14

uten

0.14

Activations Density 0.282%

information related to structured timeframes and cycles, particularly in formalized contexts like trials or programs

No Comments

No Known Activations