INDEX

Explanations

references to the "Avengers" franchise 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 @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

itten

-0.17

oler

-0.17

away

-0.17

okud

-0.16

unte

-0.15

éĥ

-0.15

igated

-0.14

indow

-0.14

iele

-0.14

onet

-0.14

POSITIVE LOGITS

ktop

0.16

oksen

0.16

ull

0.15

hes

0.15

 anch

0.15

eye

0.14

eshire

0.14

ullo

0.14

roll

0.14

Activations Density 0.003%

references to the "Avengers" franchise in various contexts

No Comments

No Known Activations