INDEX

Explanations

specific quantities and limitations regarding resources or regulations

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

ensa

-0.18

isko

-0.15

 compl

-0.14

ÙĨÙħ

-0.14

ono

-0.14

erval

-0.14

rending

-0.14

anning

-0.14

osa

-0.14

POSITIVE LOGITS

per

0.18

 available

0.18

 involved

0.16

 needed

0.16

ativo

0.16

ailable

0.16

idend

0.15

 necessary

0.15

needed

0.15

pard

0.15

Activations Density 0.133%

specific quantities and limitations regarding resources or regulations

No Comments

No Known Activations