INDEX

Explanations

past tense verbs indicating actions or events that have occurred

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

.zh

-0.15

itesse

-0.14

 Weiss

-0.14

ivot

-0.14

edula

-0.14

iyah

-0.14

PLIC

-0.13

ÑĻ

-0.13

iba

-0.13

POSITIVE LOGITS

mue

0.15

->__

0.15

å¥Ī

0.14

áºŃu

0.14

éħ

0.14

Calibri

0.14

 schÃ¶n

0.13

ĥn

0.13

rends

0.13

Ð°Ð»Ð¾Ð²

0.13

Activations Density 1.410%

past tense verbs indicating actions or events that have occurred

No Comments

No Known Activations