INDEX

Explanations

mentions of activity-related contexts, especially regarding various tasks and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

AGMA

-0.18

_ASSUME

-0.15

ornings

-0.14

amespace

-0.14

tableFuture

-0.13

ÑĩÐµÑģÐºÐ¸Ñħ

-0.13

_mD

-0.13

\<^

-0.13

Ð¸ÑĩÐµÑģÐºÐ¾Ðµ

-0.13

.Xr

-0.13

POSITIVE LOGITS

 activity

0.95

 activities

0.82

activity

0.80

 Activity

0.80

 activ

0.72

Activity

0.72

 Activities

0.71

æ´»åĬ¨

0.70

activities

0.69

_activity

0.68

Activations Density 0.202%

mentions of activity-related contexts, especially regarding various tasks and responsibilities

No Comments

No Known Activations