INDEX

Explanations

topics related to negotiation and management programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ido

-0.15

lint

-0.14

 Shelf

-0.14

enha

-0.14

ulan

-0.14

lant

-0.14

odash

-0.14

CUR

-0.13

atts

-0.13

ALLE

-0.13

POSITIVE LOGITS

 depths

0.20

 Into

0.20

into

0.20

 fray

0.19

 into

0.19

 INTO

0.18

 fold

0.18

 midst

0.17

 shoes

0.17

 folds

0.17

Activations Density 0.261%

topics related to negotiation and management programs

No Comments

No Known Activations