INDEX

Explanations

responses indicating success or failure in a process

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

stash

-0.18

anela

-0.16

.lesson

-0.15

outil

-0.15

uv

-0.15

ÑĢÑĮ

-0.15

amo

-0.14

entic

-0.14

kv

-0.14

ityEngine

-0.14

POSITIVE LOGITS

/results

0.17

ough

0.16

 SetProperty

0.15

oved

0.15

 Pension

0.15

ãĥ´

0.15

 next

0.14

 Skull

0.14

 gras

0.14

_irq

0.14

Activations Density 0.405%

responses indicating success or failure in a process

No Comments

No Known Activations