INDEX

Explanations

occurrences of the word "una" 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

kov

-0.17

anta

-0.15

hall

-0.14

odor

-0.14

ium

-0.14

antro

-0.14

ater

-0.13

Ã¶rÃ¼

-0.13

ãĥ³ãĥĲ

-0.13

gel

-0.13

POSITIVE LOGITS

isper

0.18

nom

0.16

ãĥ³ãĤ¬

0.15

ÃŃÅĻ

0.15

.pref

0.15

erate

0.14

/stdc

0.14

etat

0.14

Haz

0.14

legs

0.14

Activations Density 0.006%

occurrences of the word "una" in various contexts

No Comments

No Known Activations