INDEX

Explanations

names and references to specific individuals, particularly those related to legal cases or significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ivity

-0.19

uro

-0.16

evin

-0.16

Ãłn

-0.15

bj

-0.15

ascript

-0.14

iper

-0.14

asis

-0.14

kinson

-0.14

mesh

-0.14

POSITIVE LOGITS

Gh

0.23

gh

0.21

gh

0.19

fÃ¶r

0.18

etto

0.17

GH

0.17

GH

0.17

áº¿

0.16

azi

0.16

ogh

0.15

Activations Density 0.020%

names and references to specific individuals, particularly those related to legal cases or significant events

No Comments

No Known Activations