INDEX

Explanations

patterns of frequency or normality in behaviors and occurrences

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

frequency adverbs

np_max-act-logits · claude-4-5-sonnet

Triggered by @sripadkarne

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

baugh

-0.16

llib

-0.16

_extraction

-0.16

abolic

-0.14

udad

-0.14

 mines

-0.14

á»ĳt

-0.14

è¾ĳ

-0.14

aniem

-0.13

 nghi

-0.13

POSITIVE LOGITS

0.16

SDK

0.15

belt

0.14

 Cocktail

0.14

chain

0.14

 suppl

0.14

ra

0.14

0.13

Mig

0.13

Activations Density 0.085%

patterns of frequency or normality in behaviors and occurrences

frequency adverbs

No Known Activations