INDEX

Explanations

references to puzzles and problem-solving concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ä»½

-0.17

readcr

-0.16

names

-0.16

å¸¯

-0.15

omi

-0.15

licher

-0.15

fol

-0.14

æ¿ĥ

-0.14

Ã¼zel

-0.14

ales

-0.14

POSITIVE LOGITS

-solving

0.18

gram

0.17

ATIC

0.17

atic

0.16

matic

0.16

 puzzles

0.16

tron

0.16

 puzzle

0.16

grams

0.15

Solver

0.15

Activations Density 0.030%

references to puzzles and problem-solving concepts

No Comments

No Known Activations