INDEX

Explanations

occurrences of specific articles and nouns 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

kop

-0.16

ichten

-0.15

agens

-0.15

erval

-0.15

nce

-0.14

 action

-0.14

olib

-0.14

à¹Ħà¸§

-0.14

pull

-0.14

POSITIVE LOGITS

 stacking

0.15

 èĢ

0.15

ï»¿↵↵

0.15

Ð·Ð²

0.15

essen

0.15

SPATH

0.14

ÙĤÙī

0.14

AMA

0.14

planet

0.14

geh

0.14

Activations Density 0.066%

occurrences of specific articles and nouns in various contexts

No Comments

No Known Activations