INDEX

Explanations

mentions of individuals and groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

(es

-0.20

ayne

-0.15

berg

-0.15

ship

-0.15

 itself

-0.14

ensis

-0.14

ï¸ı

-0.14

piel

-0.14

ts

-0.14

dev

-0.14

POSITIVE LOGITS

/entities

0.24

who

0.22

/groups

0.19

hood

0.18

who

0.17

 Ø§ÙĦØ°ÙĬÙĨ

0.16

/devices

0.15

 whom

0.15

nels

0.15

/entity

0.15

Activations Density 0.130%

mentions of individuals and groups

No Comments

No Known Activations