INDEX

Explanations

verbs and related terms associated with instruction, construction, and infection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ed

-0.23

ISTIC

-0.19

ftar

-0.18

edBy

-0.17

ALLY

-0.16

istically

-0.16

atoria

-0.16

ality

-0.16

neys

-0.15

awaiter

-0.15

POSITIVE LOGITS

ive

0.52

ors

0.48

ivity

0.44

ively

0.44

IVE

0.37

ives

0.37

iveness

0.35

ible

0.31

ORS

0.30

ivo

0.29

Activations Density 0.084%

verbs and related terms associated with instruction, construction, and infection

No Comments

No Known Activations