INDEX

Explanations

occurrences of the letter "l" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Rosenstein

-0.17

_vlog

-0.17

ï»¿#

-0.16

$LANG

-0.16

tember

-0.16

CLR

-0.15

ÑıÐº

-0.15

_produk

-0.15

:maj

-0.14

blr

-0.14

POSITIVE LOGITS

loc

0.21

ÃŃn

0.19

levant

0.19

locs

0.18

lat

0.18

illa

0.17

ÙĦÙĩ

0.17

let

0.17

led

0.17

loan

0.17

Activations Density 0.002%

occurrences of the letter "l" and its variations

No Comments

No Known Activations