INDEX

Explanations

references to specific events or details from prior posts or sections

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

lech

-0.15

 opaque

-0.15

AMS

-0.14

 ÏħÏĢÎ¬ÏģÏĩÎ¿ÏħÎ½

-0.14

dere

-0.14

ucci

-0.14

uo

-0.14

antor

-0.14

uele

-0.13

uids

-0.13

POSITIVE LOGITS

onga

0.17

ÑģÑĮ

0.15

_executor

0.15

à¤¼à¤°

0.15

igin

0.15

 originally

0.14

+","+

0.14

 original

0.14

²

0.14

uder

0.14

Activations Density 0.139%

references to specific events or details from prior posts or sections

No Comments

No Known Activations