INDEX

Explanations

variables and keywords associated with data structures or identifiers in programming 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

awi

-0.16

eniz

-0.16

imdi

-0.15

azzi

-0.15

ÙĪØ·

-0.14

ä¸ĺ

-0.14

oxid

-0.14

Î¬Ïĥ

-0.14

uire

-0.14

POSITIVE LOGITS

ãĤ¦ãĥĪ

0.16

ga

0.14

mos

0.14

opy

0.14

Ð°Ð½Ð¸ÑĨ

0.14

 marginal

0.14

unger

0.14

Ð¾Ð»Ð¶

0.14

.br

0.13

sez

0.13

Activations Density 0.007%

variables and keywords associated with data structures or identifiers in programming contexts

No Comments

No Known Activations