INDEX

Explanations

technical terms related to mathematical concepts and proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

elt

-0.15

 asympt

-0.14

imiter

-0.14

bay

-0.13

æĳĺ

-0.13

templ

-0.13

 hypothesis

-0.13

DECL

-0.13

abay

-0.13

Sa

-0.13

POSITIVE LOGITS

 explicit

0.23

 Necessary

0.22

 necessary

0.20

 conditions

0.19

 Conditions

0.19

necessary

0.19

 explicitly

0.18

 existence

0.18

 CONDITIONS

0.18

 formula

0.18

Activations Density 0.234%

technical terms related to mathematical concepts and proofs

No Comments

No Known Activations