INDEX

Explanations

discussions on historical political processes and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

egot

-0.16

pto

-0.15

ÑħÐ¸

-0.14

QE

-0.14

eg

-0.14

elder

-0.14

Î³Îº

-0.14

_fifo

-0.14

 Flip

-0.14

POSITIVE LOGITS

 conduct

0.20

conduct

0.18

 fabric

0.17

hur

0.16

 wider

0.16

enne

0.15

alin

0.15

á»ĵn

0.15

wel

0.15

Activations Density 0.309%

discussions on historical political processes and their implications

No Comments

No Known Activations