INDEX

Explanations

patterns of closing punctuation marks 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

abox

-0.15

_overlay

-0.15

.strict

-0.15

ÑĮÐºÐ¾

-0.14

/proto

-0.14

roof

-0.14

etine

-0.13

ube

-0.13

ãĤ¦ãĥ³

-0.13

POSITIVE LOGITS

bas

0.18

 âĹĦ

0.15

 Denn

0.15

BAS

0.14

bler

0.14

.Dispatch

0.14

 Mines

0.14

tainment

0.14

Cached

0.14

itizer

0.14

Activations Density 0.027%

patterns of closing punctuation marks in various contexts

No Comments

No Known Activations