INDEX

Explanations

occurrences of the word "review" and its related forms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

çĮ®

-0.18

-0.17

orr

-0.16

-0.15

van

-0.15

uco

-0.14

ingu

-0.14

ÅĻÃŃÅ¾

-0.14

umpt

-0.13

POSITIVE LOGITS

izu

0.17

ollar

0.17

ovÃ¡n

0.16

pton

0.15

anke

0.15

itta

0.14

(::

0.14

iÃ³n

0.14

itan

0.14

AGMA

0.14

Activations Density 0.023%

occurrences of the word "review" and its related forms

No Comments

No Known Activations