INDEX

Explanations

sentences describing outcomes or results of various scenarios

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

anc

-0.19

ombok

-0.16

hev

-0.14

 Ferr

-0.14

anos

-0.14

 Sachs

-0.14

 Nack

-0.14

amber

-0.14

itz

-0.13

apesh

-0.13

POSITIVE LOGITS

qml

0.15

 result

0.15

utzer

0.15

Extern

0.14

effect

0.14

estination

0.14

 risult

0.14

(effect

0.14

 outcome

0.14

 Ð¸ÑĤÐ¾Ð³

0.14

Activations Density 0.068%

sentences describing outcomes or results of various scenarios

No Comments

No Known Activations