INDEX

Explanations

expressions of positive experiences or sentiments, particularly related to benefits or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

.struts

-0.16

.true

-0.15

 pero

-0.15

ff

-0.14

æĪĲäºº

-0.14

ip

-0.14

ument

-0.13

jom

-0.13

.dk

-0.13

POSITIVE LOGITS

hek

0.19

éĲ

0.15

@Spring

0.15

ogs

0.15

hausen

0.15

ÎµÏĦ

0.15

hawks

0.14

ONUS

0.14

qli

0.14

ktop

0.14

Activations Density 0.194%

expressions of positive experiences or sentiments, particularly related to benefits or outcomes

No Comments

No Known Activations