INDEX

Explanations

key technical terms and structure within a programming context

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

mons

-0.17

vers

-0.15

atz

-0.15

-0.14

ken

-0.14

 Ents

-0.14

iegel

-0.14

kit

-0.14

Kit

-0.14

Kit

-0.13

POSITIVE LOGITS

_SCHEMA

0.18

 CDDL

0.17

#/

0.17

Joi

0.16

xbd

0.16

 Ingram

0.15

_schema

0.15

 Schema

0.15

ç¨¿

0.15

PATCH

0.15

Activations Density 0.041%

key technical terms and structure within a programming context

No Comments

No Known Activations