INDEX

Explanations

specific nouns and terms related to various topics and contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ickey

-0.16

ARP

-0.16

 Hicks

-0.15

ply

-0.15

irk

-0.15

emand

-0.15

ping

-0.14

lessly

-0.14

Var

-0.14

 Gilbert

-0.14

POSITIVE LOGITS

roti

0.16

serter

0.15

ibase

0.15

ãĥ§

0.15

akit

0.14

Ð°Ð¼ÐµÑĤ

0.14

ãĥĨãĥ«

0.14

 ç»

0.14

elib

0.13

Activations Density 0.021%

specific nouns and terms related to various topics and contexts

No Comments

No Known Activations