INDEX

Explanations

specific numerical values and references to objects, events, or sections within texts

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

adir

-0.15

_SQL

-0.14

ooks

-0.14

 interrupted

-0.14

 raft

-0.13

Ð²Ð¸Ñħ

-0.13

ummer

-0.13

qq

-0.13

 clam

-0.13

nici

-0.13

POSITIVE LOGITS

Fif

0.17

antics

0.16

enson

0.15

awi

0.15

mot

0.14

ldkf

0.14

 PRODUCTS

0.14

fin

0.13

rd

0.13

ardash

0.13

Activations Density 0.189%

specific numerical values and references to objects, events, or sections within texts

No Comments

No Known Activations