INDEX

Explanations

information about filmography and television series, including roles and seasons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

addin

-0.19

exampleModal

-0.17

Ð»Ð°Ð³Ð°

-0.17

_hdl

-0.16

.nlm

-0.16

-toggler

-0.15

.nasa

-0.15

Ä±rak

-0.15

ÎŃÏģ

-0.15

psz

-0.15

POSITIVE LOGITS

 slide

0.15

ification

0.14

upo

0.14

ÐµÑģÑĤ

0.14

acies

0.14

 attendance

0.13

 Brass

0.13

ignment

0.13

rag

0.13

 consum

0.13

Activations Density 0.001%

information about filmography and television series, including roles and seasons

No Comments

No Known Activations