INDEX

Explanations

terms related to attributes and properties in 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 @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

edException

-0.18

ÅĻik

-0.16

WithIdentifier

-0.15

enga

-0.15

mun

-0.14

TIME

-0.14

ancellable

-0.14

eren

-0.14

_FLUSH

-0.14

evity

-0.14

POSITIVE LOGITS

0.15

oldemort

0.15

ifix

0.15

ÏįÏĢ

0.15

ourcem

0.14

_audit

0.14

oud

0.14

audit

0.14

unix

0.14

ascus

0.14

Activations Density 0.061%

terms related to attributes and properties in a programming context

No Comments

No Known Activations