INDEX

Explanations

positive feedback or evaluations of experiences and services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

-0.15

ëį°ìĿ´íĬ¸

-0.14

-0.12

ãĥ¼ãĥ¼

-0.12

.datatables

-0.12

.wp

-0.12

 coinc

-0.11

íĨłíĨł

-0.11

ëĶĶìĭľ

-0.11

 succ

-0.11

POSITIVE LOGITS

 [âĢ¦

0.23

 âĢĲ

0.16

ħĮ

0.15

 [âĢ¦]

0.15

 frauen

0.14

 erotische

0.14

âĢĲ

0.14

’ÑıÑĤ

0.13

:@""

0.13

 councill

0.13

Activations Density 4.619%

positive feedback or evaluations of experiences and services

No Comments

No Known Activations