INDEX

Explanations

sentences indicating understanding or realization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ãģ°ãģĭãĤĬ

-0.15

IRROR

-0.15

eni

-0.15

æĢ¥

-0.15

asz

-0.15

anÃ¡

-0.14

ensis

-0.14

ature

-0.14

former

-0.13

atk

-0.13

POSITIVE LOGITS

 exactly

0.20

 instantly

0.19

 Exactly

0.19

 deep

0.18

Exactly

0.17

 immediately

0.16

 they

0.16

 beyond

0.16

[((

0.16

ape

0.15

Activations Density 0.052%

sentences indicating understanding or realization

No Comments

No Known Activations