INDEX

Explanations

mentions of relationships or structures involving groups or categories

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

-0.17

Interop

-0.16

orny

-0.15

whatever

-0.14

both

-0.14

quelle

-0.14

['__

-0.13

quisite

-0.13

avel

-0.13

POSITIVE LOGITS

emens

0.14

icia

0.14

Ãłn

0.13

ishlist

0.13

/of

0.13

lasses

0.13

idot

0.13

kontakte

0.13

âĶĶ

0.13

rog

0.12

Activations Density 0.219%

mentions of relationships or structures involving groups or categories

No Comments

No Known Activations