INDEX

Explanations

words or symbols related to scoring or success in competitive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

valuator

-0.16

VX

-0.14

ogui

-0.14

 Chronicle

-0.13

 Automation

-0.13

etic

-0.13

uten

-0.13

annis

-0.13

irit

-0.13

Ã©tica

-0.13

POSITIVE LOGITS

 recovery

0.34

 Recovery

0.29

 sparse

0.29

 dictionary

0.27

 reconstruction

0.27

 recovering

0.26

 recover

0.26

 compress

0.25

 compressed

0.25

 signal

0.24

Activations Density 0.006%

words or symbols related to scoring or success in competitive contexts

No Comments

No Known Activations