INDEX

Explanations

function definitions and invocations within code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

.hu

-0.17

ÃŃc

-0.16

aight

-0.15

Ã³ng

-0.15

agem

-0.15

.option

-0.15

rouch

-0.15

-option

-0.14

ãĥĥãĥģ

-0.14

ayer

-0.14

POSITIVE LOGITS

anzi

0.15

ippets

0.15

maf

0.15

maal

0.14

PT

0.14

Ð»Ð¸Ð²

0.14

iese

0.14

 mixed

0.14

 Persona

0.14

ASA

0.14

Activations Density 0.284%

function definitions and invocations within code

No Comments

No Known Activations