INDEX

Explanations

past participles and forms of the verb "to find" 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 @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ãĥ¼ãĥ«

-0.16

arith

-0.14

ethoven

-0.14

Ð¿Ð¾Ð²

-0.14

emens

-0.14

igraph

-0.14

ëª

-0.14

INDEX

-0.14

acci

-0.14

loth

-0.14

POSITIVE LOGITS

uty

0.16

odable

0.16

sono

0.15

ssql

0.15

ãĤ§

0.14

icens

0.14

 Freder

0.14

essian

0.14

(found

0.13

ÏĦÎ¹Î±

0.13

Activations Density 0.111%

past participles and forms of the verb "to find" in various contexts

No Comments

No Known Activations