INDEX

Explanations

terms related to the appropriateness or suitability of options and solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

Ã´me

-0.17

OOK

-0.16

erland

-0.15

stad

-0.15

êµ°ìļĶ

-0.14

 há»

-0.14

leanup

-0.14

ens

-0.14

hazi

-0.14

 Podesta

-0.14

POSITIVE LOGITS

inus

0.14

 Ð´Ð»Ñı

0.14

-fit

0.14

atron

0.14

 untuk

0.14

 Stevenson

0.14

atorium

0.13

McN

0.13

wis

0.13

handle

0.13

Activations Density 0.172%

terms related to the appropriateness or suitability of options and solutions

No Comments

No Known Activations