INDEX

Explanations

occurrences of the word "to" 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

utar

-0.16

ãĥ¼ãĥĭ

-0.15

ennes

-0.15

akter

-0.14

ophy

-0.14

apel

-0.14

yny

-0.14

Ëĺ

-0.14

ibold

-0.13

ufe

-0.13

POSITIVE LOGITS

\:

0.15

Du

0.15

ÏģÎ¹Î±

0.14

rosso

0.14

Ð¾ÑĤÐ¸

0.14

lien

0.14

anje

0.14

du

0.13

aeda

0.13

icros

0.13

Activations Density 0.338%

occurrences of the word "to" in various contexts

No Comments

No Known Activations