INDEX

Explanations

instances of specific names, terms, or titles that hold significance in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Ð¾Ð»Ð¾Ð²

-0.16

 subsidi

-0.15

Ð³Ð¾ÑĢÐ¾Ð´

-0.15

-parse

-0.14

 ãĢĳ

-0.14

 Norris

-0.14

ä¸Ī

-0.14

_drv

-0.14

.modules

-0.14

abox

-0.14

POSITIVE LOGITS

oidal

0.17

 Mund

0.15

oid

0.14

oure

0.14

kir

0.14

Ú©Ø§Ø±ÛĮ

0.14

Î´Î¬

0.14

ÏĦÎ¹

0.14

haven

0.13

avar

0.13

Activations Density 0.333%

instances of specific names, terms, or titles that hold significance in various contexts

No Comments

No Known Activations