INDEX

Explanations

phrases related to eligibility and participation criteria in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

im

-0.17

-0.16

 GÃ¤

-0.15

mal

-0.15

mas

-0.14

mal

-0.14

 pole

-0.14

 Thornton

-0.14

Ral

-0.14

on

-0.14

POSITIVE LOGITS

.nlm

0.17

rena

0.16

plib

0.16

RITE

0.15

orz

0.15

edii

0.14

.struts

0.14

 involved

0.14

ENA

0.14

umd

0.14

Activations Density 0.345%

phrases related to eligibility and participation criteria in various contexts

No Comments

No Known Activations