INDEX

Explanations

keywords indicating uncertainty or conditionality about subjects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

irit

-0.13

 therein

-0.12

áº¬

-0.12

gregar

-0.11

fifo

-0.11

ira

-0.10

Ãµi

-0.10

cul

-0.10

rouch

-0.10

POSITIVE LOGITS

OLUTE

0.13

CADE

0.12

 nutshell

0.12

.scalablytyped

0.11

iglia

0.11

bestos

0.11

senal

0.11

ableObject

0.11

ForResource

0.11

aycast

0.10

Activations Density 0.015%

keywords indicating uncertainty or conditionality about subjects

No Comments

No Known Activations