INDEX

Explanations

phrases referencing legal, financial, or ethical responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

opsis

-0.18

aban

-0.16

nil

-0.15

Nil

-0.15

oola

-0.15

UDA

-0.14

uncture

-0.14

á»¯u

-0.14

preci

-0.14

ALCHEMY

-0.14

POSITIVE LOGITS

olle

0.16

icer

0.15

ahead

0.14

hei

0.14

 interior

0.14

Online

0.14

.ai

0.13

redo

0.13

å½

0.13

 Online

0.13

Activations Density 0.027%

phrases referencing legal, financial, or ethical responsibilities

No Comments

No Known Activations