INDEX

Explanations

references to events or productions in a temporal context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

obel

-0.20

 Relay

-0.16

 nouve

-0.15

enha

-0.15

cken

-0.15

Æ°á»¡ng

-0.14

ould

-0.14

ouden

-0.14

abilia

-0.14

_SYS

-0.14

POSITIVE LOGITS

 carrier

0.15

ç«Ł

0.15

Ø§ÛĮØ§ÙĨ

0.14

 Ð¿ÑĢÐµÐ´ÐµÐ»

0.14

Å¾el

0.14

GridColumn

0.14

kanÄ±

0.14

_REUSE

0.14

carrier

0.14

Activations Density 0.015%

references to events or productions in a temporal context

No Comments

No Known Activations