INDEX

Explanations

references to downloadable PDF files and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

encer

-0.18

ÙĦØ§Øª

-0.14

erate

-0.14

ssl

-0.14

 Steele

-0.13

ccione

-0.13

.plugin

-0.13

float

-0.13

 tapes

-0.13

ograd

-0.13

POSITIVE LOGITS

.mit

0.15

GOR

0.14

olean

0.14

_NOP

0.14

uraa

0.13

opis

0.13

 Perf

0.13

ekt

0.13

Timeout

0.13

ups

0.13

Activations Density 0.003%

references to downloadable PDF files and related terms

No Comments

No Known Activations