INDEX

Explanations

instances of the word "story," indicating a focus on narratives or recounting events

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

mamak

-0.15

sons

-0.15

STD

-0.14

quent

-0.14

stry

-0.14

 Sadd

-0.14

isay

-0.14

mare

-0.13

ģn

-0.13

UIScreen

-0.13

POSITIVE LOGITS

0.16

oring

0.16

ulle

0.15

MOOTH

0.15

 Higher

0.14

heim

0.14

ount

0.14

igner

0.14

evice

0.14

(parseFloat

0.13

Activations Density 0.027%

instances of the word "story," indicating a focus on narratives or recounting events

No Comments

No Known Activations