INDEX

Explanations

elements related to instability or decline, particularly in a psychological or performance context

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

adge

-0.16

FRING

-0.15

Playable

-0.15

/Runtime

-0.15

icari

-0.15

GestureRecognizer

-0.15

GMT

-0.14

mdir

-0.14

ÅĽci

-0.14

ucci

-0.14

POSITIVE LOGITS

au

0.16

ffa

0.15

ala

0.14

 runner

0.14

ale

0.14

lee

0.14

ahan

0.14

 noqa

0.14

ol

0.14

aul

0.13

Activations Density 0.040%

elements related to instability or decline, particularly in a psychological or performance context

No Comments

No Known Activations