INDEX

Explanations

terms related to experimental setups or scientific terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

-0.16

çļ

-0.15

å¯Ħ

-0.15

chein

-0.14

pell

-0.14

ÏĦÎŃ

-0.14

/apis

-0.14

elder

-0.14

undle

-0.13

POSITIVE LOGITS

 regul

0.16

IM

0.15

indo

0.14

Ð¾ÑĤÐ¾Ð²

0.14

MAC

0.14

isman

0.14

 endeavour

0.14

owi

0.13

aklÄ±

0.13

am

0.13

Activations Density 0.038%

terms related to experimental setups or scientific terminology

No Comments

No Known Activations