INDEX

Explanations

occurrences of template syntax or programming placeholders within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

avad

-0.19

ores

-0.14

_FS

-0.14

cription

-0.14

ÑĥÐºÐ°

-0.13

_consts

-0.13

 Circular

-0.13

 tops

-0.13

áº¯n

-0.13

ude

-0.12

POSITIVE LOGITS

ë¬¼

0.16

apons

0.16

 Neuroscience

0.15

0.14

ctal

0.14

0.13

upil

0.13

åĩī

0.13

/examples

0.13

 Kara

0.13

Activations Density 0.001%

occurrences of template syntax or programming placeholders within the text

No Comments

No Known Activations